def __init__(self,
sampledata,
refdata,
job_params,
outdir,
libdir,
umi,
maxcores=1,
scratch="/scratch/tmp/tmp",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir,
libdir, umi, maxcores, scratch, **kwargs)
# Set the min alt frac value:
self.default_job_params["vardict-min-alt-frac"] = 0.01
self.default_job_params["vardict-min-num-reads"] = None
self.default_job_params[
"vep-additional-options"] = " --pick --filter_common "
# Remove clinseq barcodes for which data is not available:
self.check_sampledata()
if umi:
# Configure the umi processes from fastq to bam file:
self.configure_umi_processing()
else:
# Configure alignment and merging of fastq data for all clinseq barcodes:
self.configure_align_and_merge()
# Configure all panel analyses:
self.configure_panel_analyses()
# Configure liqbio-specific panel analyses:
self.configure_panel_analyses_liqbio(umi)
# Configure additional msings analysis:
self.configure_panel_msings_analyses()
# Configure QC of all panel data:
self.configure_all_panel_qcs()
# Configure fastq QCs:
self.configure_fastq_qcs()
# Configure the low-pass whole genome analysis:
self.configure_lowpass_analyses()
# Configure low-pass whole genome data QC:
self.configure_all_lowpass_qcs()
# Configure MultiQC:
self.configure_multi_qc()
def __init__(self,
sampledata,
refdata,
job_params,
outdir,
libdir,
maxcores=1,
scratch="/scratch/tmp/tmp/",
referral_db_conf="tests/referrals/referral-db-config.json",
addresses="tests/referrals/addresses.csv",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir,
libdir, maxcores, scratch, **kwargs)
self.referral_db_conf = referral_db_conf
self.addresses = addresses
self.default_job_params["vardict-min-num-reads"] = 6
self.default_job_params["create_alascca_report"] = True
# Check to ensure that the sample data is valid for an ALASCCA analysis:
self.validate_sample_data_for_alascca()
# Remove sample capture items for which data is not available:
self.check_sampledata()
# Configure alignment and merging of fastq data for all clinseq barcodes:
self.configure_align_and_merge()
# Configure all panel analyses:
self.configure_panel_analyses()
# Configure QC of all panel data:
self.configure_all_panel_qcs()
# Configure ALASCCA report generation:
self.configure_alascca_specific_analysis()
# Configure fastq QCs:
self.configure_fastq_qcs()
# Configure MultiQC:
self.configure_multi_qc()
def setUp(self):
sample_data = {
"sdid":
"P-NA12877",
"T": [
"AL-P-NA12877-T-03098849-TD1-TT1",
"AL-P-NA12877-T-03098849-TD1-WGS"
],
"N": [
"AL-P-NA12877-N-03098121-TD1-TT1",
"AL-P-NA12877-N-03098121-TD1-WGS"
],
"CFDNA": [
"LB-P-NA12877-CFDNA-03098850-TD1-TT1",
"LB-P-NA12877-CFDNA-03098850-TD1-TT2",
"LB-P-NA12877-CFDNA-03098850-TD1-WGS"
]
}
ref_data = {
"bwaIndex": "bwa/test-genome-masked.fasta",
"chrsizes": "genome/test-genome-masked.chrsizes.txt",
"clinvar": "variants/clinvar_20160203.vcf.gz",
"cosmic": "variants/CosmicCodingMuts_v71.vcf.gz",
"dbSNP": "variants/dbsnp142-germline-only.vcf.gz",
"exac": "variants/ExAC.r0.3.1.sites.vep.vcf.gz",
"icgc":
"variants/icgc_release_20_simple_somatic_mutation.aggregated.vcf.gz",
"reference_dict": "genome/test-genome-masked.dict",
"reference_genome": "genome/test-genome-masked.fasta",
"swegene_common": "variants/swegen_common.vcf.gz",
"targets": {
"test-regions": {
"cnvkit-ref":
None,
"msisites":
"intervals/targets/test-regions.msisites.tsv",
"targets-bed-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.bed",
"targets-interval_list":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list",
"targets-interval_list-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list"
}
},
"contest_vcfs": {
"test-regions": "test_contest.vcf"
},
"vep_dir": None
}
self.test_clinseq_pipeline = ClinseqPipeline(
sample_data, ref_data, {}, "/tmp", "/nfs/LIQBIO/INBOX/exomes")
def __init__(self, sampledata, refdata, job_params, outdir, libdir, umi, maxcores=1, scratch="/scratch/tmp/tmp",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir, libdir, umi,
maxcores, scratch, **kwargs)
# Set the min alt frac value:
self.default_job_params["vardict-min-alt-frac"] = 0.01
self.default_job_params["vardict-min-num-reads"] = None
self.default_job_params["vep-additional-options"] = " --pick --filter_common "
#Set initial data
self.sampledata = sampledata
self.refdata = refdata
self.job_params = job_params
self.outdir = outdir
self.libdir = libdir
self.umi = umi
self.maxcores = maxcores
self.scratch = scratch
self.kwargs = kwargs
self.somatic_merge_vcf = defaultdict(dict)
#Below dictionary will set the steps to run aws batch job with docker image (key: docker image name , value: function to add job).
self.step_to_run = {
"qc": self.qc_step, #docker: base
"alignment": self.alignment_step, #docker: aligner
"cnvkit": self.cnvkit_step, #docker: variants
"germline_variant": self.germline_variant_step, #docker: variants
"somatic_vardict": self.somatic_variant_vardict_step, #docker: variants # tested working
"somatic_strelka": self.somatic_variant_strelka_step, #docker: variants #tested working
"somatic_mutect2": self.somatic_variant_mutect2_step, #docker: variants #tested working
"somatic_varscan": self.somatic_variant_varscan_step, #docker: variants #tested working
"somatic_variant_merge": self.somatic_variant_merge_step, #docker: somaticseq #tested working
"vep": self.vep_step, #docker : vep #tested
"msi" : self.msi_sensor_step
}
def setUp(self):
self.sample_data = {
"sdid":
"P-00202345",
"N": ["LB-P-00202345-N-03277090-TP20190201-CP20190204"],
"T": [],
"CFDNA": [
"LB-P-00202345-CFDNA-03277089-TP20190201-CP20190204",
"LB-P-00202345-CFDNA-03277089-TP20190201-CM20190204"
]
}
self.ref_data = {
"bwaIndex": "bwa/test-genome-masked.fasta",
"chrsizes": "genome/test-genome-masked.chrsizes.txt",
"clinvar": "variants/clinvar_20160203.vcf.gz",
"cosmic": "variants/CosmicCodingMuts_v71.vcf.gz",
"dbSNP": "variants/dbsnp142-germline-only.vcf.gz",
"exac": "variants/ExAC.r0.3.1.sites.vep.vcf.gz",
"icgc":
"variants/icgc_release_20_simple_somatic_mutation.aggregated.vcf.gz",
"reference_dict": "genome/test-genome-masked.dict",
"reference_genome": "genome/test-genome-masked.fasta",
"swegene_common": "variants/swegen_common.vcf.gz",
"ar_regions": "intervals/ar_regions.bed",
"ts_regions": "intervals/ts_regions.bed",
"fusion_regions": "intervals/fusion_regions.bed",
"1KG":
"/nfs/ALASCCA/autoseq-genome/variants/1000G_phase1.indels.b37.vcf.gz",
"Mills_and_1KG_gold_standard":
"/nfs/ALASCCA/autoseq-genome/variants/Mills_and_1000G_gold_standard.indels.b37.vcf.gz",
"brca_exchange":
"/nfs/ALASCCA/autoseq-genome/variants/BrcaExchangeClinvar_15Jan2019_v26_hg19.vcf.gz",
"oncokb":
"/nfs/ALASCCA/autoseq-genome/variants/OncoKB_6Mar19_v1.9.txt",
"targets": {
"test-regions": {
"cnvkit-ref": {
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnn",
"N":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.N.cnn"
}
},
"cnvkit-fix": {
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnvkit-fix.tsv"
}
},
"msisites": "intervals/targets/test-regions.msisites.tsv",
"targets-bed-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.bed",
"targets-interval_list":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list",
"targets-interval_list-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list",
"blacklist-bed": None,
"purecn_targets": "intervals/targets/purecn.bed",
},
"progression": {
"blacklist-bed":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.blacklist.bed",
"cnvkit-fix": {
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnvkit-fix.tsv"
}
},
"cnvkit-ref": {
"KAPA_HYPERPREP": {
"N":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.KAPA_HYPERPREP.N.cnn",
"T":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.KAPA_HYPERPREP.T.cnn"
},
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnn",
"N":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.THRUPLEX_PLASMASEQ.N.cnn"
}
},
"msings-baseline":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.msings.baseline",
"msings-bed":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.msings.bed",
"msings-msi_intervals":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.msings.msi_intervals",
"msisites":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.slopped20.msisites.tsv",
"purecn_targets":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.purecn.txt",
"targets-bed-slopped20":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.slopped20.bed.gz",
"targets-interval_list":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.interval_list",
"targets-interval_list-slopped20":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/progression.slopped20.interval_list"
},
"monitor": {
"blacklist-bed":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/monitor.blacklist.bed",
"msings-baseline":
None,
"msings-bed":
None,
"msings-msi_intervals":
None,
"msisites":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/monitor.slopped20.msisites.tsv",
"purecn_targets":
None,
"targets-bed-slopped20":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/monitor.slopped20.bed.gz",
"targets-interval_list":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/monitor.interval_list",
"targets-interval_list-slopped20":
"/nfs/ALASCCA/autoseq-genome/intervals/targets/monitor.slopped20.interval_list"
}
},
"contest_vcfs": {
"test-regions": "test_contest.vcf"
},
"vep_dir": "dummy_vep_dir"
}
self.test_tumor_capture = UniqueCapture("LB", "P-00202345", "CFDNA",
"03277089", "TP", "CP")
self.test_normal_capture = UniqueCapture("LB", "P-00202345", "N",
"03277090", "TP", "CP")
self.test_clinseq_pipeline = ClinseqPipeline(
self.sample_data, self.ref_data, {}, "/tmp/liqbio-test/",
"/media/clinseq/disk4/PROBIO/", 'FALSE')
def setUp(self):
sample_data = {
"sdid":
"P-NA12877",
"T": [
"AL-P-NA12877-T-03098849-TD1-TT1",
"AL-P-NA12877-T-03098849-TD1-WGS"
],
"N": [
"AL-P-NA12877-N-03098121-TD1-TT1",
"AL-P-NA12877-N-03098121-TD1-WGS"
],
"CFDNA": [
"LB-P-NA12877-CFDNA-03098850-TD1-TT1",
"LB-P-NA12877-CFDNA-03098850-TD1-TT2",
"LB-P-NA12877-CFDNA-03098850-TD1-WGS"
]
}
self.ref_data = {
"bwaIndex": "bwa/test-genome-masked.fasta",
"chrsizes": "genome/test-genome-masked.chrsizes.txt",
"clinvar": "variants/clinvar_20160203.vcf.gz",
"cosmic": "variants/CosmicCodingMuts_v71.vcf.gz",
"dbSNP": "variants/dbsnp142-germline-only.vcf.gz",
"exac": "variants/ExAC.r0.3.1.sites.vep.vcf.gz",
"icgc":
"variants/icgc_release_20_simple_somatic_mutation.aggregated.vcf.gz",
"reference_dict": "genome/test-genome-masked.dict",
"reference_genome": "genome/test-genome-masked.fasta",
"swegene_common": "variants/swegen_common.vcf.gz",
"ar_regions": "intervals/ar_regions.bed",
"ts_regions": "intervals/ts_regions.bed",
"fusion_regions": "intervals/fusion_regions.bed",
"targets": {
"test-regions": {
"cnvkit-ref": {
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnn",
"N":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.N.cnn"
}
},
"cnvkit-fix": {
"THRUPLEX_PLASMASEQ": {
"CFDNA":
"intervals/targets/progression.THRUPLEX_PLASMASEQ.CFDNA.cnvkit-fix.tsv"
}
},
"msisites": "intervals/targets/test-regions.msisites.tsv",
"targets-bed-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.bed",
"targets-interval_list":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list",
"targets-interval_list-slopped20":
"intervals/targets/test-regions-GRCh37.slopped20.interval_list",
"blacklist-bed": None,
"purecn_targets": "intervals/targets/purecn.bed",
}
},
"contest_vcfs": {
"test-regions": "test_contest.vcf"
},
"vep_dir": "dummy_vep_dir"
}
self.test_cancer_capture = UniqueCapture("AL", "P-NA12877", "CFDNA",
"03098850", "TD", "TT")
self.test_normal_capture = UniqueCapture("AL", "P-NA12877", "N",
"03098121", "TD", "TT")
self.test_clinseq_pipeline = ClinseqPipeline(
sample_data, self.ref_data, {}, "/tmp", "/nfs/LIQBIO/INBOX/exomes")